Add new CrossEncoder model

README.md

@@ -0,0 +1,502 @@
+---
+language:
+- en
+tags:
+- sentence-transformers
+- cross-encoder
+- generated_from_trainer
+- dataset_size:78704
+- loss:ListMLELoss
+base_model: microsoft/MiniLM-L12-H384-uncased
+datasets:
+- microsoft/ms_marco
+pipeline_tag: text-ranking
+library_name: sentence-transformers
+metrics:
+- map
+- mrr@10
+- ndcg@10
+model-index:
+- name: CrossEncoder based on microsoft/MiniLM-L12-H384-uncased
+  results:
+  - task:
+      type: cross-encoder-reranking
+      name: Cross Encoder Reranking
+    dataset:
+      name: NanoMSMARCO R100
+      type: NanoMSMARCO_R100
+    metrics:
+    - type: map
+      value: 0.0213
+      name: Map
+    - type: mrr@10
+      value: 0.0129
+      name: Mrr@10
+    - type: ndcg@10
+      value: 0.0388
+      name: Ndcg@10
+  - task:
+      type: cross-encoder-reranking
+      name: Cross Encoder Reranking
+    dataset:
+      name: NanoNFCorpus R100
+      type: NanoNFCorpus_R100
+    metrics:
+    - type: map
+      value: 0.2783
+      name: Map
+    - type: mrr@10
+      value: 0.4359
+      name: Mrr@10
+    - type: ndcg@10
+      value: 0.291
+      name: Ndcg@10
+  - task:
+      type: cross-encoder-reranking
+      name: Cross Encoder Reranking
+    dataset:
+      name: NanoNQ R100
+      type: NanoNQ_R100
+    metrics:
+    - type: map
+      value: 0.0331
+      name: Map
+    - type: mrr@10
+      value: 0.018
+      name: Mrr@10
+    - type: ndcg@10
+      value: 0.077
+      name: Ndcg@10
+  - task:
+      type: cross-encoder-nano-beir
+      name: Cross Encoder Nano BEIR
+    dataset:
+      name: NanoBEIR R100 mean
+      type: NanoBEIR_R100_mean
+    metrics:
+    - type: map
+      value: 0.1109
+      name: Map
+    - type: mrr@10
+      value: 0.1556
+      name: Mrr@10
+    - type: ndcg@10
+      value: 0.1356
+      name: Ndcg@10
+---
+
+# CrossEncoder based on microsoft/MiniLM-L12-H384-uncased
+
+This is a [Cross Encoder](https://www.sbert.net/docs/cross_encoder/usage/usage.html) model finetuned from [microsoft/MiniLM-L12-H384-uncased](https://huggingface.co/microsoft/MiniLM-L12-H384-uncased) on the [ms_marco](https://huggingface.co/datasets/microsoft/ms_marco) dataset using the [sentence-transformers](https://www.SBERT.net) library. It computes scores for pairs of texts, which can be used for text reranking and semantic search.
+
+## Model Details
+
+### Model Description
+- **Model Type:** Cross Encoder
+- **Base model:** [microsoft/MiniLM-L12-H384-uncased](https://huggingface.co/microsoft/MiniLM-L12-H384-uncased) <!-- at revision 44acabbec0ef496f6dbc93adadea57f376b7c0ec -->
+- **Maximum Sequence Length:** 512 tokens
+- **Number of Output Labels:** 1 label
+- **Training Dataset:**
+    - [ms_marco](https://huggingface.co/datasets/microsoft/ms_marco)
+- **Language:** en
+<!-- - **License:** Unknown -->
+
+### Model Sources
+
+- **Documentation:** [Sentence Transformers Documentation](https://sbert.net)
+- **Documentation:** [Cross Encoder Documentation](https://www.sbert.net/docs/cross_encoder/usage/usage.html)
+- **Repository:** [Sentence Transformers on GitHub](https://github.com/UKPLab/sentence-transformers)
+- **Hugging Face:** [Cross Encoders on Hugging Face](https://huggingface.co/models?library=sentence-transformers&other=cross-encoder)
+
+## Usage
+
+### Direct Usage (Sentence Transformers)
+
+First install the Sentence Transformers library:
+
+```bash
+pip install -U sentence-transformers
+```
+
+Then you can load this model and run inference.
+```python
+from sentence_transformers import CrossEncoder
+
+# Download from the 🤗 Hub
+model = CrossEncoder("yjoonjang/reranker-msmarco-v1.1-MiniLM-L12-H384-uncased-plistmle-customweight-sigmoid")
+# Get scores for pairs of texts
+pairs = [
+    ['How many calories in an egg', 'There are on average between 55 and 80 calories in an egg depending on its size.'],
+    ['How many calories in an egg', 'Egg whites are very low in calories, have no fat, no cholesterol, and are loaded with protein.'],
+    ['How many calories in an egg', 'Most of the calories in an egg come from the yellow yolk in the center.'],
+]
+scores = model.predict(pairs)
+print(scores.shape)
+# (3,)
+
+# Or rank different texts based on similarity to a single text
+ranks = model.rank(
+    'How many calories in an egg',
+    [
+        'There are on average between 55 and 80 calories in an egg depending on its size.',
+        'Egg whites are very low in calories, have no fat, no cholesterol, and are loaded with protein.',
+        'Most of the calories in an egg come from the yellow yolk in the center.',
+    ]
+)
+# [{'corpus_id': ..., 'score': ...}, {'corpus_id': ..., 'score': ...}, ...]
+```
+
+<!--
+### Direct Usage (Transformers)
+
+<details><summary>Click to see the direct usage in Transformers</summary>
+
+</details>
+-->
+
+<!--
+### Downstream Usage (Sentence Transformers)
+
+You can finetune this model on your own dataset.
+
+<details><summary>Click to expand</summary>
+
+</details>
+-->
+
+<!--
+### Out-of-Scope Use
+
+*List how the model may foreseeably be misused and address what users ought not to do with the model.*
+-->
+
+## Evaluation
+
+### Metrics
+
+#### Cross Encoder Reranking
+
+* Datasets: `NanoMSMARCO_R100`, `NanoNFCorpus_R100` and `NanoNQ_R100`
+* Evaluated with [<code>CrossEncoderRerankingEvaluator</code>](https://sbert.net/docs/package_reference/cross_encoder/evaluation.html#sentence_transformers.cross_encoder.evaluation.CrossEncoderRerankingEvaluator) with these parameters:
+  ```json
+  {
+      "at_k": 10,
+      "always_rerank_positives": true
+  }
+  ```
+
+| Metric      | NanoMSMARCO_R100     | NanoNFCorpus_R100    | NanoNQ_R100          |
+|:------------|:---------------------|:---------------------|:---------------------|
+| map         | 0.0213 (-0.4683)     | 0.2783 (+0.0173)     | 0.0331 (-0.3865)     |
+| mrr@10      | 0.0129 (-0.4646)     | 0.4359 (-0.0639)     | 0.0180 (-0.4087)     |
+| **ndcg@10** | **0.0388 (-0.5017)** | **0.2910 (-0.0340)** | **0.0770 (-0.4236)** |
+
+#### Cross Encoder Nano BEIR
+
+* Dataset: `NanoBEIR_R100_mean`
+* Evaluated with [<code>CrossEncoderNanoBEIREvaluator</code>](https://sbert.net/docs/package_reference/cross_encoder/evaluation.html#sentence_transformers.cross_encoder.evaluation.CrossEncoderNanoBEIREvaluator) with these parameters:
+  ```json
+  {
+      "dataset_names": [
+          "msmarco",
+          "nfcorpus",
+          "nq"
+      ],
+      "rerank_k": 100,
+      "at_k": 10,
+      "always_rerank_positives": true
+  }
+  ```
+
+| Metric      | Value                |
+|:------------|:---------------------|
+| map         | 0.1109 (-0.2791)     |
+| mrr@10      | 0.1556 (-0.3124)     |
+| **ndcg@10** | **0.1356 (-0.3198)** |
+
+<!--
+## Bias, Risks and Limitations
+
+*What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.*
+-->
+
+<!--
+### Recommendations
+
+*What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.*
+-->
+
+## Training Details
+
+### Training Dataset
+
+#### ms_marco
+
+* Dataset: [ms_marco](https://huggingface.co/datasets/microsoft/ms_marco) at [a47ee7a](https://huggingface.co/datasets/microsoft/ms_marco/tree/a47ee7aae8d7d466ba15f9f0bfac3b3681087b3a)
+* Size: 78,704 training samples
+* Columns: <code>query</code>, <code>docs</code>, and <code>labels</code>
+* Approximate statistics based on the first 1000 samples:
+  |         | query                                                                                          | docs                                                                                   | labels                                                                                 |
+  |:--------|:-----------------------------------------------------------------------------------------------|:---------------------------------------------------------------------------------------|:---------------------------------------------------------------------------------------|
+  | type    | string                                                                                         | list                                                                                   | list                                                                                   |
+  | details | <ul><li>min: 11 characters</li><li>mean: 33.21 characters</li><li>max: 89 characters</li></ul> | <ul><li>min: 3 elements</li><li>mean: 6.50 elements</li><li>max: 10 elements</li></ul> | <ul><li>min: 3 elements</li><li>mean: 6.50 elements</li><li>max: 10 elements</li></ul> |
+* Samples:
+  | query                                                 | docs                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                     | labels                            |
+  |:------------------------------------------------------|:---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:----------------------------------|
+  | <code>how fast can spaceships go</code>               | <code>["The International Space Station travels in orbit around Earth at a speed of roughly 17,150 miles per hour (that's about 5 miles per second!). This means that the Space Station orbits Earth (and sees a sunrise) once every 92 minutes!", "Best Answer: Light is the physical speed limit of the Universe (as far as we know) (scientists take great pains not to declare anything conclusively because things have a habit of being disproven) and the answerer was right, that's about 186,000 miles per second-or - 300,000 kilometers per second.", 'Launched by NASA in 2006, it shot directly to a solar system escape velocity. This consisted of an Earth-relative launch of 16.26 kilometers a second (that’s about 36,000 miles per hour), plus a velocity component from Earth’s orbital motion (which is 30 km/s tangential to the orbital path).', "How fast does a spaceship travel in Earth's orbit and is there a sense of speed? The international space station (taken as an example) orbits earth once every 92 mi...</code> | <code>[1, 0, 0, 0, 0, ...]</code> |
+  | <code>what is an autoimmune disease definition</code> | <code>["autoimmune disease, one of a large group of diseases characterized by altered function of the immune system of the body, resulting in the production of antibodies against the body's own cells. Some autoimmune disorders, such as Hashimoto's disease, are tissue specific, whereas others, such as SLE, affect multiple organs and systems. Both genetic and environmental triggers may contribute to autoimmune disease. About 5-8% of the U.S. population is affected by an", "Lupus is a chronic inflammatory disease that occurs when your body's immune system attacks your own tissues and organs. Inflammation caused by lupus can affect many different body systems — including your joints, skin, kidneys, blood cells, brain, heart and lungs. ", "Autoimmune diseases arise from an abnormal immune response of the body against substances and tissues normally present in the body (autoimmunity). For a disease to be regarded as an autoimmune disease it needs to answer to Witebsky's postulates (first formulate...</code> | <code>[1, 0, 0, 0, 0, ...]</code> |
+  | <code>what is a Slingbox</code>                       | <code>["A Slingbox is an audio-video (AV) device that you can use to watch and control your TV wherever you are, on your desktop or laptop computer, phone, tablet, and more. This is called placeshifting. A Slingbox connects to your TV's set-top box, your TV, and your home network.", 'Slingbox Software. Slingbox works in conjunction with the SlingPlayer software you install on your computer. Together, they sling NTSC or PAL video data to another location. It works with regular TV, satellite TV, cable TV, a DVD player, DVR or camcorder.', 'The network connector on the Slingbox then connects to your Internet router with a standard ethernet cable, or wirelessly with a special bridge adapter. An infrared cable from the Slingbox, pointed at your TV or DVR gives you the ability to remotely control them from your computer.', 'The Slingbox is a TV streaming media device made by Sling Media that encodes local video for transmission over the Internet to a remote device (sometimes called placeshifting)....</code> | <code>[1, 0, 0, 0, 0, ...]</code> |
+* Loss: [<code>ListMLELoss</code>](https://sbert.net/docs/package_reference/cross_encoder/losses.html#listmleloss) with these parameters:
+  ```json
+  {
+      "lambda_weight": "sentence_transformers.cross_encoder.losses.ListMLELoss.ListMLELambdaWeight",
+      "activation_fct": "torch.nn.modules.activation.Sigmoid",
+      "mini_batch_size": 16,
+      "respect_input_order": true
+  }
+  ```
+
+### Evaluation Dataset
+
+#### ms_marco
+
+* Dataset: [ms_marco](https://huggingface.co/datasets/microsoft/ms_marco) at [a47ee7a](https://huggingface.co/datasets/microsoft/ms_marco/tree/a47ee7aae8d7d466ba15f9f0bfac3b3681087b3a)
+* Size: 1,000 evaluation samples
+* Columns: <code>query</code>, <code>docs</code>, and <code>labels</code>
+* Approximate statistics based on the first 1000 samples:
+  |         | query                                                                                          | docs                                                                                   | labels                                                                                 |
+  |:--------|:-----------------------------------------------------------------------------------------------|:---------------------------------------------------------------------------------------|:---------------------------------------------------------------------------------------|
+  | type    | string                                                                                         | list                                                                                   | list                                                                                   |
+  | details | <ul><li>min: 11 characters</li><li>mean: 33.49 characters</li><li>max: 98 characters</li></ul> | <ul><li>min: 2 elements</li><li>mean: 6.00 elements</li><li>max: 10 elements</li></ul> | <ul><li>min: 2 elements</li><li>mean: 6.00 elements</li><li>max: 10 elements</li></ul> |
+* Samples:
+  | query                                                                | docs                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                     | labels                            |
+  |:---------------------------------------------------------------------|:---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:----------------------------------|
+  | <code>where is the great wall of china located</code>                | <code>['Home Other Information Great Wall Facts. Where is the Great Wall of china located？. The Great Wall stretches across North China from east to west for over 6,000 kilometers. It extends from the shanhai pass at the seaside in the Hebei province in the east to the Jiayu pass in Gansu province in the west. The sites of the Great Wall stretch across 15 provinces of China. But since the great wall in Beijing is very long and protected well while most of the great walls in other China areas are not kept well and opened for tourists, it is commonly thought Beijing is the only place to see the Great Wall.', 'The Great Wall is not located in any one given city. Some areas of the Great Wall offer magnificent vistas and picture-perfect brick-and-stone watchtowers, whereas older, pre-Ming areas may be in disrepair yet would certainly impress any archeology aficionado. Very early parts of the Great Wall were constructed from tamped-earth and, where possible, stone.', 'Our Great Wall maps cover the...</code> | <code>[1, 0, 0, 0, 0, ...]</code> |
+  | <code>do dogs get any nutrition from vegetables</code>               | <code>["Just as fruits and vegetables are considered healthy foods for humans, they can also help prolong a dog's life. Orange, red and yellow fruits and vegetables are best for dogs because they are often nutrient-dense [source: Donomor ]. Many fruits and vegetables also contain antioxidants that reduce the risk of cancer. But not all fruits and vegetables are healthy for your dog. Avoid serving your dog dyed, waxed, or genetically engineered foods; just as with humans, organic foods are best.", 'A good way for dogs to get the full nutrients of the vegetables is to break them down in a pureed form. No matter how you prepare the vegetables for your dogs, do not use salt. Dogs don’t always care for it and it is not good for dogs with heart conditions.', "Despite the belief that dogs are strictly carnivorous, they're actually omnivores that eat a wide variety of plant material -- even in the wild. Like humans, dogs require the nutrients found in a host of vegetables and fruits; however, a few ...</code> | <code>[1, 0, 0, 0, 0, ...]</code> |
+  | <code>what type of sonnet is composed upon westminster bridge</code> | <code>['From Wikipedia, the free encyclopedia.  Composed upon Westminster Bridge, September 3, 1802  is a Petrarchan sonnet by William Wordsworth describing London and the River Thames, viewed from Westminster Bridge in the early morning. It was first published in the collection Poems, in Two Volumes in 1807. ', "Type of Work. Composed Upon Westminster Bridge is a lyric poem in the form of a sonnet. In English, there are two types of sonnets, the Petrarchan and the Shakespearean, both with fourteen lines. Wordsworth's poem is a Petrarchan sonnet, developed by the Italian poet Petrarch (1304-1374), a Roman Catholic priest. Wordsworth's sonnet Composed upon Westminster Bridge, September 3, 1802 falls into the category of Momentary Poems. The poet is describing what he sees, thinks and feels on a specific day at a specific moment. Had September 3, 1802, been a dismal day of rain, fog or overcast skies, we would not have this lyric to enjoy.", "Rhyme Scheme and Meter. .......The rhyme scheme of ...</code> | <code>[1, 0, 0, 0, 0, ...]</code> |
+* Loss: [<code>ListMLELoss</code>](https://sbert.net/docs/package_reference/cross_encoder/losses.html#listmleloss) with these parameters:
+  ```json
+  {
+      "lambda_weight": "sentence_transformers.cross_encoder.losses.ListMLELoss.ListMLELambdaWeight",
+      "activation_fct": "torch.nn.modules.activation.Sigmoid",
+      "mini_batch_size": 16,
+      "respect_input_order": true
+  }
+  ```
+
+### Training Hyperparameters
+#### Non-Default Hyperparameters
+
+- `eval_strategy`: steps
+- `per_device_train_batch_size`: 16
+- `per_device_eval_batch_size`: 16
+- `learning_rate`: 2e-05
+- `num_train_epochs`: 1
+- `warmup_ratio`: 0.1
+- `seed`: 12
+- `bf16`: True
+- `load_best_model_at_end`: True
+
+#### All Hyperparameters
+<details><summary>Click to expand</summary>
+
+- `overwrite_output_dir`: False
+- `do_predict`: False
+- `eval_strategy`: steps
+- `prediction_loss_only`: True
+- `per_device_train_batch_size`: 16
+- `per_device_eval_batch_size`: 16
+- `per_gpu_train_batch_size`: None
+- `per_gpu_eval_batch_size`: None
+- `gradient_accumulation_steps`: 1
+- `eval_accumulation_steps`: None
+- `torch_empty_cache_steps`: None
+- `learning_rate`: 2e-05
+- `weight_decay`: 0.0
+- `adam_beta1`: 0.9
+- `adam_beta2`: 0.999
+- `adam_epsilon`: 1e-08
+- `max_grad_norm`: 1.0
+- `num_train_epochs`: 1
+- `max_steps`: -1
+- `lr_scheduler_type`: linear
+- `lr_scheduler_kwargs`: {}
+- `warmup_ratio`: 0.1
+- `warmup_steps`: 0
+- `log_level`: passive
+- `log_level_replica`: warning
+- `log_on_each_node`: True
+- `logging_nan_inf_filter`: True
+- `save_safetensors`: True
+- `save_on_each_node`: False
+- `save_only_model`: False
+- `restore_callback_states_from_checkpoint`: False
+- `no_cuda`: False
+- `use_cpu`: False
+- `use_mps_device`: False
+- `seed`: 12
+- `data_seed`: None
+- `jit_mode_eval`: False
+- `use_ipex`: False
+- `bf16`: True
+- `fp16`: False
+- `fp16_opt_level`: O1
+- `half_precision_backend`: auto
+- `bf16_full_eval`: False
+- `fp16_full_eval`: False
+- `tf32`: None
+- `local_rank`: 0
+- `ddp_backend`: None
+- `tpu_num_cores`: None
+- `tpu_metrics_debug`: False
+- `debug`: []
+- `dataloader_drop_last`: False
+- `dataloader_num_workers`: 0
+- `dataloader_prefetch_factor`: None
+- `past_index`: -1
+- `disable_tqdm`: False
+- `remove_unused_columns`: True
+- `label_names`: None
+- `load_best_model_at_end`: True
+- `ignore_data_skip`: False
+- `fsdp`: []
+- `fsdp_min_num_params`: 0
+- `fsdp_config`: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
+- `fsdp_transformer_layer_cls_to_wrap`: None
+- `accelerator_config`: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}
+- `deepspeed`: None
+- `label_smoothing_factor`: 0.0
+- `optim`: adamw_torch
+- `optim_args`: None
+- `adafactor`: False
+- `group_by_length`: False
+- `length_column_name`: length
+- `ddp_find_unused_parameters`: None
+- `ddp_bucket_cap_mb`: None
+- `ddp_broadcast_buffers`: False
+- `dataloader_pin_memory`: True
+- `dataloader_persistent_workers`: False
+- `skip_memory_metrics`: True
+- `use_legacy_prediction_loop`: False
+- `push_to_hub`: False
+- `resume_from_checkpoint`: None
+- `hub_model_id`: None
+- `hub_strategy`: every_save
+- `hub_private_repo`: None
+- `hub_always_push`: False
+- `gradient_checkpointing`: False
+- `gradient_checkpointing_kwargs`: None
+- `include_inputs_for_metrics`: False
+- `include_for_metrics`: []
+- `eval_do_concat_batches`: True
+- `fp16_backend`: auto
+- `push_to_hub_model_id`: None
+- `push_to_hub_organization`: None
+- `mp_parameters`: 
+- `auto_find_batch_size`: False
+- `full_determinism`: False
+- `torchdynamo`: None
+- `ray_scope`: last
+- `ddp_timeout`: 1800
+- `torch_compile`: False
+- `torch_compile_backend`: None
+- `torch_compile_mode`: None
+- `dispatch_batches`: None
+- `split_batches`: None
+- `include_tokens_per_second`: False
+- `include_num_input_tokens_seen`: False
+- `neftune_noise_alpha`: None
+- `optim_target_modules`: None
+- `batch_eval_metrics`: False
+- `eval_on_start`: False
+- `use_liger_kernel`: False
+- `eval_use_gather_object`: False
+- `average_tokens_across_devices`: False
+- `prompts`: None
+- `batch_sampler`: batch_sampler
+- `multi_dataset_batch_sampler`: proportional
+
+</details>
+
+### Training Logs
+| Epoch      | Step     | Training Loss | Validation Loss | NanoMSMARCO_R100_ndcg@10 | NanoNFCorpus_R100_ndcg@10 | NanoNQ_R100_ndcg@10  | NanoBEIR_R100_mean_ndcg@10 |
+|:----------:|:--------:|:-------------:|:---------------:|:------------------------:|:-------------------------:|:--------------------:|:--------------------------:|
+| -1         | -1       | -             | -               | 0.0377 (-0.5027)         | 0.2892 (-0.0359)          | 0.0433 (-0.4573)     | 0.1234 (-0.3320)           |
+| 0.0002     | 1        | 10.5987       | -               | -                        | -                         | -                    | -                          |
+| 0.0508     | 250      | 10.1157       | -               | -                        | -                         | -                    | -                          |
+| 0.1016     | 500      | 9.8615        | 9.9241          | 0.0149 (-0.5255)         | 0.2942 (-0.0308)          | 0.0494 (-0.4512)     | 0.1195 (-0.3358)           |
+| 0.1525     | 750      | 9.8392        | -               | -                        | -                         | -                    | -                          |
+| 0.2033     | 1000     | 9.8483        | 9.9147          | 0.0434 (-0.4970)         | 0.2995 (-0.0256)          | 0.0585 (-0.4421)     | 0.1338 (-0.3216)           |
+| 0.2541     | 1250     | 9.8496        | -               | -                        | -                         | -                    | -                          |
+| 0.3049     | 1500     | 9.8151        | 9.9134          | 0.0247 (-0.5157)         | 0.2981 (-0.0269)          | 0.0663 (-0.4343)     | 0.1297 (-0.3256)           |
+| 0.3558     | 1750     | 9.8153        | -               | -                        | -                         | -                    | -                          |
+| **0.4066** | **2000** | **9.8081**    | **9.9129**      | **0.0388 (-0.5017)**     | **0.2910 (-0.0340)**      | **0.0770 (-0.4236)** | **0.1356 (-0.3198)**       |
+| 0.4574     | 2250     | 9.8519        | -               | -                        | -                         | -                    | -                          |
+| 0.5082     | 2500     | 9.835         | 9.9127          | 0.0349 (-0.5056)         | 0.2944 (-0.0307)          | 0.0551 (-0.4455)     | 0.1281 (-0.3272)           |
+| 0.5591     | 2750     | 9.8854        | -               | -                        | -                         | -                    | -                          |
+| 0.6099     | 3000     | 9.843         | 9.9126          | 0.0488 (-0.4916)         | 0.2848 (-0.0402)          | 0.0689 (-0.4317)     | 0.1342 (-0.3212)           |
+| 0.6607     | 3250     | 9.8305        | -               | -                        | -                         | -                    | -                          |
+| 0.7115     | 3500     | 9.875         | 9.9125          | 0.0420 (-0.4985)         | 0.2797 (-0.0453)          | 0.0634 (-0.4372)     | 0.1284 (-0.3270)           |
+| 0.7624     | 3750     | 9.8414        | -               | -                        | -                         | -                    | -                          |
+| 0.8132     | 4000     | 9.8326        | 9.9125          | 0.0449 (-0.4955)         | 0.2820 (-0.0430)          | 0.0704 (-0.4302)     | 0.1324 (-0.3229)           |
+| 0.8640     | 4250     | 9.9309        | -               | -                        | -                         | -                    | -                          |
+| 0.9148     | 4500     | 9.8191        | 9.9124          | 0.0460 (-0.4944)         | 0.2821 (-0.0430)          | 0.0567 (-0.4440)     | 0.1282 (-0.3271)           |
+| 0.9656     | 4750     | 9.8501        | -               | -                        | -                         | -                    | -                          |
+| -1         | -1       | -             | -               | 0.0388 (-0.5017)         | 0.2910 (-0.0340)          | 0.0770 (-0.4236)     | 0.1356 (-0.3198)           |
+
+* The bold row denotes the saved checkpoint.
+
+### Framework Versions
+- Python: 3.11.11
+- Sentence Transformers: 3.5.0.dev0
+- Transformers: 4.49.0
+- PyTorch: 2.6.0+cu124
+- Accelerate: 1.5.2
+- Datasets: 3.4.0
+- Tokenizers: 0.21.1
+
+## Citation
+
+### BibTeX
+
+#### Sentence Transformers
+```bibtex
+@inproceedings{reimers-2019-sentence-bert,
+    title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
+    author = "Reimers, Nils and Gurevych, Iryna",
+    booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
+    month = "11",
+    year = "2019",
+    publisher = "Association for Computational Linguistics",
+    url = "https://arxiv.org/abs/1908.10084",
+}
+```
+
+#### ListMLELoss
+```bibtex
+@inproceedings{lan2013position,
+    title={Position-aware ListMLE: a sequential learning process for ranking},
+    author={Lan, Yanyan and Guo, Jiafeng and Cheng, Xueqi and Liu, Tie-Yan},
+    booktitle={Proceedings of the Twenty-Ninth Conference on Uncertainty in Artificial Intelligence},
+    pages={333--342},
+    year={2013}
+}
+```
+
+<!--
+## Glossary
+
+*Clearly define terms in order to be accessible across audiences.*
+-->
+
+<!--
+## Model Card Authors
+
+*Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
+-->
+
+<!--
+## Model Card Contact
+
+*Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
+-->

config.json

@@ -0,0 +1,34 @@
+{
+  "_name_or_path": "microsoft/MiniLM-L12-H384-uncased",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 384,
+  "id2label": {
+    "0": "LABEL_0"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 1536,
+  "label2id": {
+    "LABEL_0": 0
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "sentence_transformers": {
+    "activation_fn": "torch.nn.modules.activation.Sigmoid"
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.49.0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:255887706f50cb8966174c13b13ccf9df4735e0792286340a24a1ea2f74f5d2a
+size 133464836

special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

tokenizer_config.json

@@ -0,0 +1,58 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": true,
+  "extra_special_tokens": {},
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}